Visual Explanation by Unifying Adversarial Generation and Feature Importance Attributions

Explaining the decisions of deep learning models is critical for their adoption in medical practice. In this work, we propose to unify existing adversarial explanation methods and path-based feature importance attribution approaches. We consider a path between the input image and a generated adversary and associate a weight depending on the model output variations along this path. We validate our attribution methods on two medical classification tasks. We demonstrate significant improvement compared to state-of-the-art methods in both feature importance attribution and localization performance.